Plugins

Local Ollama worker tools for DeepSeek Harness: model inventory, a single unverified ask, and a batch runner that chunks long text, checks every item deterministically, returns a small verbatim sample for review and can optionally write the labelled result inside the session workspace.

Manages the lifecycle of the local UM GenAI proxy (127.0.0.1:8788) that DSH's um-genai provider talks to: wakes it on demand for llm/stream calls, stops it after an idle period, and reports health plus a read-only status endpoint. Also ships a DSH settings page for port, always-on mode, idle minutes, interpreter and paths, plus the UM account and proxy API key, and a button that writes the providers.um-genai entry into the profile patch and fills in its model list, since a fresh profile has no provider and the model picker would otherwise stay empty. A renewal watchdog logs in to the campus gateway on a hidden Windows desktop when the upstream token expires. The proxy itself is um_opencode_setup.py, a single-file tool distributed by the University of Macau; a copy is vendored in vendor/ so a fresh install works out of the box, while a copy in ~/.um-opencode/ takes precedence when present. The plugin still does not produce tokens: those come from logging in to the campus gateway. Requires Windows (process discovery and idle shutdown use netstat/taskkill; renewal uses PowerShell and a hidden desktop), Python 3.10+ and a University of Macau account.

Fills in a cheaper sibling route for subagent calls that name no provider, model or effort (for example Opus to Sonnet 5.5 at medium, Qwen max to Qwen flash); explicit choices and subagent_fork are left alone. Requires the subagent-model-selection policy to be enabled with the target route in its allowedModels - without it the plugin does nothing.

Antigravity provider for DeepSeek Harness: resolves the OAuth client from the locally installed official desktop app and supports multiple accounts with quota-based automatic switching.

Signs in to LightVela by WeChat QR code, reads the model gateway key from your own instance and writes the gateway into llm-pi-ai so its models appear in the picker.

Talks to the two public Hugging Face Spaces (MiniMax-VL-01 and Llama-2-7B-Chat) that grok3ai.org only embeds in an iframe, presenting them as OpenAI-compatible models.

Runs a local OpenAI-compatible relay that forwards DSH chat requests to grok.online, exposing its two chat models in the model picker without an API key.

DeepSeek Harness sidebar for LiteLLM models, MCP servers, skills, and spend.

Huawei Cloud CodeArts provider for DeepSeek Harness with OAuth2 PKCE/DPoP sign-in, multi-account rotation, model discovery, and credits and usage views. A derivative of elegant01/dsh-codearts (MIT) with added account and image features; do not install it alongside the upstream - both register the same `codearts` provider.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

Prompt manager for DSH: imports prompts from JSON or Markdown sources and DSH's own system sections, then controls what is injected into the system prompt — per prompt, or per agent preset — with title editing, drag ordering, LLM translation and the option to inject either the original text or its translation.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

DeepSeek Harness (dsh) plugin: say "clear everything above" and old turns stop being sent to the model, saving tokens. Also works for Cherry Studio.

Claude-Code-compatible memory for every model in DeepSeek Harness: layered CLAUDE.md/AGENTS.md instructions with @import and rules, a persistent MEMORY.md memory with full writing guidance, refresh on resume and compaction, optional recall, background ext

Quota pill for DeepSeek Harness: remaining quota for every LLM subscription you have, in one collapsible pill

Adds a Git chip beside the composer that opens a centered workbench (changes, history, files, tags, stash) plus a Git section in settings. Supports multi-account OAuth device flow and PAT with per-repository permissions (full, read, none), gates writes behind a global switch and reads behind an allowed-directory list, and refuses a push whose target remote belongs to no writable account. Diffs preview in place with line numbers, four layouts, word-level emphasis, syntax highlighting and Ctrl/⌘+F find; Markdown and images render inline, commit messages are searchable, and commit messages can be generated from the staged diff through the host LLM service. Ships 8 Agent tools, 51 local HTTP endpoints and 8 languages, with tokens encrypted at rest by AES-256-GCM.

Strips AI-flavor from LLM text with local density scanning and deterministic fact/strength/safety checks; a rewrite that fails verification falls back to the original.

[LLM] 使 DSH 能从 magpie 上游同步输入模态及 thinking level

DeepSeek Harness plugin that starts each Vercel AI Gateway conversation on the fastest provider for its model

AOCI-CODE cognition layer for DeepSeek Harness: one-shot /aoci command + dynamic MCP bridge for governed, Git-versioned repository/database cognition.

Youdao-style word-selection translation for the DSH web GUI. Select text anywhere, click the floating button, get a translation — by default through keyless public translation endpoints, with the harness's own LLM as the other engine. 有道风格划词翻译：DSH Web GUI

Local-first resume warehouse for DeepSeek Harness: one tool to start/stop the local app and read its health. Everything stays on this machine; the only outbound path is a configurable LLM API.

提示词工作台：优化、多轮迭代，并可直接在新对话中使用

模型报错时自动切到备用模型并在同一步重试，备用模型可在设置页从模型列表里选。